Created
September 25, 2018 03:24
-
-
Save susanli2016/7d42db7f099eb81f62c17756952e4080 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
def get_vectors(model, corpus_size, vectors_size, vectors_type): | |
""" | |
Get vectors from trained doc2vec model | |
:param doc2vec_model: Trained Doc2Vec model | |
:param corpus_size: Size of the data | |
:param vectors_size: Size of the embedding vectors | |
:param vectors_type: Training or Testing vectors | |
:return: list of vectors | |
""" | |
vectors = np.zeros((corpus_size, vectors_size)) | |
for i in range(0, corpus_size): | |
prefix = vectors_type + '_' + str(i) | |
vectors[i] = model.docvecs[prefix] | |
return vectors | |
train_vectors_dbow = get_vectors(model_dbow, len(X_train), 300, 'Train') | |
test_vectors_dbow = get_vectors(model_dbow, len(X_test), 300, 'Test') |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment